arXiv subjects

Chenyang Cao

Publications and source records attributed to Chenyang Cao.

10 recordsLinked to original sources

arXiv2026

Push-Wiper: Toward General-Purpose Robotic Cleaning across Varied Stains and Surfaces with Segmented Pushing Trajectories

Viscous stains, characterized by high viscosity and complex rheological properties, remain a major challenge for robotic surface cleaning. Conventional wiping often spreads the stain, while scrubbing provides stronger friction but risks damaging the surface. In this paper, we propose Push-Wiper, a framework that reformulates viscous stain cleaning as an aggregation problem. Push-Wiper employs a sponge to progressively gather stains through segmented pushing trajectories, followed by a post-processing phase that detaches the aggregated material and enables sponge self-cleaning. We adopt a stepwise strategy for stain gathering and leverage Diffusion Policy to generate adaptive pushing action sequences. These sequences are executed through our Arbitrary Surface Pose Interpolator (ASPI) and a hybrid force-position controller, allowing the method to generalize to stains with diverse spatial distributions. Push-Wiper achieves a cleaning score (CS), defined as the percentage of stain area removed, up to 130% higher than baseline methods. Without additional training, Push-Wiper also transfers in a zero-shot manner to solid residues, liquid spills, unseen viscous stains, and curved surfaces with varying geometries. Our experiments demonstrate the cleaning effectiveness of Push-Wiper and its strong generalization ability. The project website is available at https://push-wiper.github.io/.

cs.RO↗

arXiv2026

Anisotropic Tensile Strength and Fracture Mechanism of $\theta$-TaN: A Machine-Learning Potential Molecular Dynamics Study

theta-phase tantalum nitride (theta-TaN) combines metallic conductivity with exceptionally high thermal conductivity, making it a potential material for device thermal management and interconnect applications. However, its tensile strength and fracture behavior remain unclear. Here, we investigate the anisotropic tensile response and fracture mechanism of theta-TaN using neuroevolution-potential molecular dynamics simulations. Size-convergence tests show that a 20 nm long model is sufficient for reliable prediction, and the mechanical parameters vary by less than 3.5% over the strain-rate range of 10^7 to 10^9 s^-1. The results reveal strong tensile anisotropy. The c-axis direction ([0001]) shows a higher strength of 80.10 GPa and modulus of 748.63 GPa, but a lower fracture strain of 15.02%. In contrast, the a-axis direction ([2-1-10]) shows a lower strength of 56.87 GPa and modulus of 570.74 GPa, but a higher fracture strain of 17.71%. From 300 to 900 K, the mechanical properties decrease nearly linearly, while more than 73% of the 300 K strength is retained at 900 K. Fracture occurs without observable dislocation activity and is governed by cleavage-plane selection: {10-10} prismatic planes under a-axis tension and the (0001) basal plane under c-axis tension. Atomic displacement analysis shows that local separation and microvoid formation precede macroscopic crack growth, indicating a brittle fracture process driven by local bond-network instability. These results provide atomic-scale mechanical data for assessing the reliability of theta-TaN in thermal management applications.

cond-mat.mtrl-sci↗

arXiv2026

QPILOTS: Efficient Test-Time Q-Steering for Flow Policies

Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy extraction requires exploiting the critic's action gradient, yet directly backpropagating this signal through a multi-step denoising process can be numerically unstable. Existing methods work around this either by discarding gradient information, distilling the policy into a simpler one-step actor, or repeatedly fine-tuning the denoising policy as the critic improves. We propose QPILOTS, a method that leaves the original policy unmodified and steers the denoising process at inference time. At each denoising step, instead of evaluating the critic on the noisy intermediate action where critic predictions are unreliable, we first project that intermediate state to an estimate of the final clean action and compute the critic gradient there. We introduce two variants: QPILOTS-U uses a fast single-point approximation, while QPILOTS-M draws differentiable posterior samples via a learned auxiliary network. On a standard offline-to-online RL benchmark, QPILOTS achieves the best aggregate performance, reaching an average success rate of 90% across 50 tasks. We also apply QPILOTS to steer a large, frozen, pretrained Vision-Language Action (VLA) foundation model, outperforming or matching prior inference-time approaches across six manipulation tasks in simulation.

cs.LG↗

arXiv2025

A universal framework for nonlinear frequency combs under electro-optic modulation

Nonlinear frequency combs, including electro-optic and Kerr combs, have become central platforms for chip-scale frequency synthesis. Recent breakthroughs in strong-coupling electro-optic modulation further expanded their accessible nonlinear dynamics, unlocking new phenomena and functionalities, but the underlying foundation remains largely unexplored. Here we establish a universal theoretical and experimental framework for nonlinear combs under arbitrary electro-optic modulation by introducing a general evolution equation (GEE) that transcends the mean-field Lugiato-Lefever equation. The GEE reduces to a discrete-time Integration Hamiltonian that provides a frequency-domain formalism unifying strong-coupling electro-optic modulation with photonic synthetic dimensions. Together with a band-wave correspondence linking modulation waveforms to synthetic band structures, the formalism enables programmable spectral control. We further show compatibility between Kerr nonlinearity and strong-coupling electro-optic modulation, highlighting their cooperative dynamics. Our work provides a foundational model for strong-coupling electro-optics in nonlinear combs, opening a route toward chip-integrated, microwave-programmable comb sources for metrology, spectroscopy, and emerging photonic technologies.

physics.optics↗

arXiv2025

Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics

Preference-based Reinforcement Learning (PbRL) provides a promising alternative to heuristic reward design in complex robotic environments. However, PbRL often suffers from poor sample efficiency, requiring extensive and costly human feedback, which limits its real-world applicability. Prior work has proposed learning a reward model from demonstrations and fine-tuning it using preferences. However, when the model is a neural network, transitioning between different loss functions across training phases often leads to unstable optimization and performance degradation. In this paper, we propose a method to effectively leverage prior knowledge with a Residual Reward Model (RRM). An RRM assumes that the true reward of the environment can be split into a sum of two parts: a prior reward and a learned reward. The prior reward is a term available before training, such as an engineering heuristic ``best guess'', a language-generated reward, or a reward function learned from inverse reinforcement learning, and the learned reward is then trained with preferences as a residual offset. Experimental results in Meta-World and DM-Control show that RRMs substantially improve the sample efficiency of common PbRL methods across various prior reward types. Furthermore, we demonstrate the practical efficacy of our method on a physical Franka Panda robot, accelerating policy learning and achieving high success rates in fewer steps than baselines.

cs.LG↗

arXiv2025

MoDE: Mixture of Diffusion Experts for Any Occluded Face Recognition

With the continuous impact of epidemics, people have become accustomed to wearing masks. However, most current occluded face recognition (OFR) algorithms lack prior knowledge of occlusions, resulting in poor performance when dealing with occluded faces of varying types and severity in reality. Recognizing occluded faces is still a significant challenge, which greatly affects the convenience of people's daily lives. In this paper, we propose an identity-gated mixture of diffusion experts (MoDE) for OFR. Each diffusion-based generative expert estimates one possible complete image for occluded faces. Considering the random sampling process of the diffusion model, which introduces inevitable differences and variations between the inpainted faces and the real ones. To ensemble effective information from multi-reconstructed faces, we introduce an identity-gating network to evaluate the contribution of each reconstructed face to the identity and adaptively integrate the predictions in the decision space. Moreover, our MoDE is a plug-and-play module for most existing face recognition models. Extensive experiments on three public face datasets and two datasets in the wild validate our advanced performance for various occlusions in comparison with the competing methods.

cs.CV↗

arXiv2025

Structural and transport properties of LiTFSI/G3 electrolyte with machine-learned molecular dynamics

The lithium bis(trifluoromethylsulfonyl)azanide-triglyme electrolyte plays a critical role in the performance of lithium-ion batteries. However, its solvation structure and transport properties at the atomic scale remain incompletely understood. In this study, we develop an efficient and accurate neuroevolution potential (NEP) model by integrating bootstrap and active learning strategies. Using machine-learned NEP-driven molecular dynamics simulations, we explore the structural and diffusion properties of LiTFSI/G3 across a wide range of the solute-to-solvent ratios, systematically analyzing electrolyte density, ion coordination, viscosity, and lithium self-diffusion. The computed densities show excellent agreement with experimental data, and pair correlation analysis reveals significant interactions between lithium ions and surrounding oxygen atoms, which strongly impacts Li$^+$ mobility. Viscosity and diffusion calculations further demonstrate that increasing LiTFSI concentration enhances Li-O interactions, resulting in higher viscosity and reduced lithium diffusion. Additionally, machine learning-based path integral molecular dynamics (PIMD) simulations confirm the negligible impact of quantum effects on Li$^+$ transport. The electrolyte-specific protocol developed in this work provides a systematic framework for constructing high-fidelity machine learning potentials for complex systems.

cond-mat.mtrl-sci↗

arXiv2024

FOSP: Fine-tuning Offline Safe Policy through World Models

Offline Safe Reinforcement Learning (RL) seeks to address safety constraints by learning from static datasets and restricting exploration. However, these approaches heavily rely on the dataset and struggle to generalize to unseen scenarios safely. In this paper, we aim to improve safety during the deployment of vision-based robotic tasks through online fine-tuning an offline pretrained policy. To facilitate effective fine-tuning, we introduce model-based RL, which is known for its data efficiency. Specifically, our method employs in-sample optimization to improve offline training efficiency while incorporating reachability guidance to ensure safety. After obtaining an offline safe policy, a safe policy expansion approach is leveraged for online fine-tuning. The performance of our method is validated on simulation benchmarks with five vision-only tasks and through real-world robot deployment using limited data. It demonstrates that our approach significantly improves the generalization of offline policies to unseen safety-constrained scenarios. To the best of our knowledge, this is the first work to explore offline-to-online RL for safe generalization tasks.

cs.RO↗

arXiv2024

Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these methods encounter limitations when dealing with diverse constraints in complex environments, such as safety constraints. Some of these approaches prioritize goal attainment without considering safety, while others excessively focus on safety at the expense of training efficiency. In this paper, we study the problem of constrained offline GCRL and propose a new method called Recovery-based Supervised Learning (RbSL) to accomplish safety-critical tasks with various goals. To evaluate the method performance, we build a benchmark based on the robot-fetching environment with a randomly positioned obstacle and use expert or random policies to generate an offline dataset. We compare RbSL with three offline GCRL algorithms and one offline safe RL algorithm. As a result, our method outperforms the existing state-of-the-art methods to a large extent. Furthermore, we validate the practicality and effectiveness of RbSL by deploying it on a real Panda manipulator. Code is available at https://github.com/Sunlighted/RbSL.git.

cs.RO↗

arXiv2023

Anisotropic and high thermal conductivity in monolayer quasi-hexagonal fullerene: A comparative study against bulk phase fullerene

Recently a novel two-dimensional (2D) C$_{60}$ based crystal called quasi-hexagonal-phase fullerene (QHPF) has been fabricated and demonstrated to be a promising candidate for 2D electronic devices [Hou et al. Nature 606, 507-510 (2022)]. We construct an accurate and transferable machine-learned potential to study heat transport and related properties of this material, with a comparison to the face-centered-cubic bulk-phase fullerene (BPF). Using the homogeneous nonequilibrium molecular dynamics and the related spectral decomposition methods, we show that the thermal conductivity in QHPF is anisotropic, which is 137(7) W/mK at 300 K in the direction parallel to the cycloaddition bonds and 102(3) W/mK in the perpendicular in-plane direction. By contrast, the thermal conductivity in BPF is isotropic and is only 0.45(5) W/mK. We show that the inter-molecular covalent bonding in QHPF plays a crucial role in enhancing the thermal conductivity in QHPF as compared to that in BPF. The heat transport properties as characterized in this work will be useful for the application of QHPF as novel 2D electronic devices.

physics.comp-ph↗